Abstract:
Breast cancer is the most common cause of death among
patients and one of the main reasons is that the lesion is not
identified properly. Ultrasound images are very difficult to
segment due to presence of speckle noise and the boundaries
of abnormal regions are too difficult to recognize due to
similarity. For this reason, proper medical facility or treatment
cannot be provided in time. The situation in Bangladesh is
alarming as there is a huge female population in the rural areas
who don’t have proper medical access to detect the early stage
of breast cancer.
We have implemented a Computer Aided Diagnosis (CAD)
system that will detect the cancerous lesion in the BUS (breast
ultrasound) images effectively. We implemented a region
growing algorithm which can segment the object of interests
(lesion). We place the seed on the ultrasound image (original
image), check homogeneity and merge the homogeneous
regions. After that we use horizontal cut based entropy
filtering and at last by canny edge detection we subtract the
object of interests (lesion) from the desired ultrasound image.
We also implemented developed watershed algorithm and
assimilated it with region growing algorithm
Description:
Supervised by
Mr. Md. Taslim Reza
Assistant Professor,
Department of Electrical and Electronic Engineering,
Islamic University of Technology (IUT), Bangladesh.
